Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

ploy.ai

Post reply on HN
Print view View original

141–144 of 144 posts

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#141

Post by vessenes »

Anon1096 wrote: post #112
vessenes wrote: post #106

Earlier quoted context omitted.

My current claude.md bans the phrase “load-bearing”, and Claude HATES that. It will troll occasionally in comments by saying things like “load-be…most specific”. Like it REALLY loves saying load-bearing. Urgh.

You are poisoning the context and priming it to say load-bearing. I don't really think there is a good way to actually ban specific phrases other than have it do a second pass, it's something baked into the model from post training.

I hear you. And, it says the phrase ALL THE TIME even without any priming. Anecdotally it’s better to complain about it. But not a lot better. I have no idea how often it’s using load bearing in the thinking traces though

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#142

Post by oakst »

jtrn wrote: post #108
SwtCyber wrote: post #95

Its ironic that under an article with a ton of deep infrastructure insights half the comments are crying about the "forced writing style". What does it matter if claude helped the author clean up the text when inside is a ready-to-use blueprint on how to save 30% of the api budget and fix empty file reads?

One of many reasons I would assume is that people just hate anything related to AI, so they latch on to anything negative they can say. Another reason is that they mean what they say... That they really, really hate the style of writing, enough to fixate on that. Personally, I think the people whining about the style are silly. Maybe because I'm terrible at grammar and spelling, but I always just focus on the message…

On the infobit, I've been trying to build in a similar completely local LLM cleanup step into Epilude. Willing to share anything you've found especially useful in producing good spellchecks/cleanups in your local setup?

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#143

Post by brcmthrowaway »

bluelightning2k wrote: post #135
brcmthrowaway wrote: post #126

AI wrapper companies still exist?

Must admit, for this particular case I don't see the appeal in using a wrapper. Why would I not just use Codex directly? The we wrote a bunch of prompts argument is kind of meh. That sort of thing has not only diminishing value with subsequent model releases but I actually believe will turn negative. The model will know better by default. For example, initially giving the model some advice on code best practice was h…

Idk man, they raised money lol
Post reply on HN